Assignment 8: Visualization - Making a bar race

How to do it?:

Open the Rmarkdown file of this assignment (link) in Rstudio.
Right under each question, insert a code chunk (you can use the hotkey Ctrl + Alt + I to add a code chunk) and code the solution for the question.
Knit the rmarkdown file (hotkey: Ctrl + Alt + K) to export an html.
Publish the html file to your Githiub Page.

Submission: Submit the link on Github of the assignment to Canvas

Install two packages gganimate and gifski then restart Rstudio. Using the Adult Census Income data, make an animation using geom_point and transition_states.

install.packages('gganimate')
install.packages('gifski')

df <- read.csv('adult_census_missing.csv')
names(df)

##  [1] "age"            "workclass"      "fnlwgt"         "education"     
##  [5] "education.num"  "marital.status" "occupation"     "relationship"  
##  [9] "race"           "sex"            "capital.gain"   "capital.loss"  
## [13] "hours.per.week" "native.country" "income"

library(gganimate)

## Warning: package 'gganimate' was built under R version 4.2.2

library(gifski)

## Warning: package 'gifski' was built under R version 4.2.2

library(ggplot2)
library(dplyr)
library(tidyverse)

df <- df %>%
  na_if("Not known") %>%
  na_if("?") %>%
  na_if("Unknown")

df <- drop_na(df)

g <- ggplot(df, aes(x = hours.per.week, y = capital.gain))+
  geom_point() + 
  transition_states(sex)+
  labs(title ='{closest_state}')
animate(g)

Using the Adult Census Income data, make an animation using geom_bar and transition_states.

g <- ggplot(df, aes(x = workclass))+
  geom_bar() + 
  transition_states(sex)+
  labs(title ='{closest_state}')
animate(g)

Use the WHO’s dataset at this link. Make a top-10 bar race by months between countries on the number of deaths by Covid 19 in 2021.

library(lubridate)
library(knitr)

df3 <- read.csv('WHO-COVID-19-global-data.csv')

df3$week <- week(df3$Date_reported)
df3 <- df3 %>% 
  group_by(week, Country) %>%
  summarise(mean = mean(New_cases)) %>%
  group_by(week) %>% mutate(rank=rank(-mean)) %>%
  filter(rank <= 10) %>%
  ggplot(aes(x=rank, y=mean, group=Country, fill=Country, label=Country)) +
  geom_col()+
  geom_text(aes(y = mean, label = Country), hjust = 1.4)+ 
    coord_flip(clip = "off", expand = FALSE) +scale_x_reverse()+
    labs(title = 'Week {closest_state}', x='', y='Number of Positive Cases', fill='Country')+
    theme(plot.title = element_text(hjust = 1, size = 22), axis.ticks.y = element_blank(), axis.text.y  = element_blank()) + 
    transition_states(week)+
    ease_aes("cubic-in-out")
animate(df3, nframes = 1000)

Make a bar race using a dataset of your own interest. You may use the dataset that we use in class (https://covidtracking.com/data/download/all-states-history.csv) but you should make a different bar racev from ones in the slides.

df4 <- read.csv('all-states-history.csv')
names(df4)

##  [1] "date"                             "state"                           
##  [3] "death"                            "deathConfirmed"                  
##  [5] "deathIncrease"                    "deathProbable"                   
##  [7] "hospitalized"                     "hospitalizedCumulative"          
##  [9] "hospitalizedCurrently"            "hospitalizedIncrease"            
## [11] "inIcuCumulative"                  "inIcuCurrently"                  
## [13] "negative"                         "negativeIncrease"                
## [15] "negativeTestsAntibody"            "negativeTestsPeopleAntibody"     
## [17] "negativeTestsViral"               "onVentilatorCumulative"          
## [19] "onVentilatorCurrently"            "positive"                        
## [21] "positiveCasesViral"               "positiveIncrease"                
## [23] "positiveScore"                    "positiveTestsAntibody"           
## [25] "positiveTestsAntigen"             "positiveTestsPeopleAntibody"     
## [27] "positiveTestsPeopleAntigen"       "positiveTestsViral"              
## [29] "recovered"                        "totalTestEncountersViral"        
## [31] "totalTestEncountersViralIncrease" "totalTestResults"                
## [33] "totalTestResultsIncrease"         "totalTestsAntibody"              
## [35] "totalTestsAntigen"                "totalTestsPeopleAntibody"        
## [37] "totalTestsPeopleAntigen"          "totalTestsPeopleViral"           
## [39] "totalTestsPeopleViralIncrease"    "totalTestsViral"                 
## [41] "totalTestsViralIncrease"

library(lubridate)
library(knitr)

df4$week <- week(df4$date)
df4 <- df4 %>% 
  group_by(week, state) %>%
  summarise(mean = mean(positive)) %>%
  group_by(week) %>% mutate(rank=rank(-mean)) %>%
  filter(rank <= 10) %>%
  ggplot(aes(x=rank, y=mean, group=state, fill=state, label=state)) +
  geom_col()+
  geom_text(aes(y = mean, label = state), hjust = 1.4)+ 
    coord_flip(clip = "off", expand = FALSE) +scale_x_reverse()+
    labs(title = 'Week {closest_state}', x='', y='Number of Positive Cases', fill='State')+
    theme(plot.title = element_text(hjust = 1, size = 22), axis.ticks.y = element_blank(), axis.text.y  = element_blank()) + 
    transition_states(week)+
    ease_aes("cubic-in-out")
animate(df3, nframes = 1000)